AIME 2024

American Invitational Mathematics Examination 2024, consisting of 30 challenging mathematical reasoning problems from AIME I and AIME II competitions. Each problem requires an integer answer between 0-999 and tests advanced mathematical reasoning across algebra, geometry, combinatorics, and number theory. Used as a benchmark for evaluating mathematical reasoning capabilities in large language models at Olympiad-level difficulty.

id aime-2024 · max 1 · 54 models reported

#	Model	Score
1	Grok-3 Mini xAI	0.96
2	o4-mini OpenAI	0.93
3	Grok-3 xAI	0.93
4	LongCat-Flash-Thinking Meituan · open	0.93
5	Gemini 2.5 Pro Google	0.92
6	o3 OpenAI	0.92
7	DeepSeek-R1-0528 DeepSeek · open	0.91
8	GLM-4.5 Zhipu AI · open	0.91
9	Ministral 3 (14B Reasoning 2512) Mistral AI · open	0.90
10	GLM-4.5-Air Zhipu AI · open	0.89
11	Gemini 2.5 Flash Google	0.88
12	o3-mini OpenAI	0.87
13	DeepSeek R1 Distill Llama 70B DeepSeek · open	0.87
14	DeepSeek R1 Zero DeepSeek · open	0.87
15	MiniMax M1 80K MiniMax · open	0.86
16	Ministral 3 (8B Reasoning 2512) Mistral AI · open	0.86
17	o1-pro OpenAI	0.86
18	Qwen3 235B A22B Alibaba Cloud / Qwen Team · open	0.86
19	MiniCPM-SALA OpenBMB · open	0.84
20	DeepSeek R1 Distill Qwen 32B DeepSeek · open	0.83
21	DeepSeek R1 Distill Qwen 7B DeepSeek · open	0.83
22	MiniMax M1 40K MiniMax · open	0.83
23	Qwen3 32B Alibaba Cloud / Qwen Team · open	0.81
24	Phi 4 Reasoning Plus Microsoft · open	0.81
25	Granite 3.3 8B Base IBM · open	0.81
26	Granite 3.3 8B Instruct IBM · open	0.81
27	Qwen3 30B A3B Alibaba Cloud / Qwen Team · open	0.80
28	Claude 3.7 Sonnet Anthropic	0.80
29	DeepSeek R1 Distill Llama 8B DeepSeek · open	0.80
30	DeepSeek R1 Distill Qwen 14B DeepSeek · open	0.80
31	QwQ-32B Alibaba Cloud / Qwen Team · open	0.80
32	Qwen3 14B Alibaba Cloud / Qwen Team · open	0.79
33	Kimi-k1.5 Moonshot AI	0.78
34	Min istral 3 (3B Reasoning 2512) Mistral AI · open	0.78
35	Phi 4 Reasoning Microsoft · open	0.75
36	o1 OpenAI	0.74
37	Magistral Medium Mistral AI · open	0.74
38	Gemini 2.0 Flash Thinking Google	0.73
39	LongCat-Flash-Lite Meituan · open	0.72
40	Kimi K2 0905 Moonshot AI	0.72
41	Magistral Small 2506 Mistral AI · open	0.71
42	Kimi K2 Instruct Moonshot AI · open	0.70
43	Kimi K2-Instruct-0905 Moonshot AI · open	0.70
44	DeepSeek-V3.1 DeepSeek · open	0.66
45	DeepSeek-V3 0324 DeepSeek · open	0.59
46	DeepSeek R1 Distill Qwen 1.5B DeepSeek · open	0.53
47	QwQ-32B-Preview Alibaba Cloud / Qwen Team · open	0.50
48	GPT-4.1 mini OpenAI	0.50
49	GPT-4.1 OpenAI	0.48
50	o1-preview OpenAI	0.42
51	DeepSeek-V3 DeepSeek · open	0.39
52	GPT-4.5 OpenAI	0.37
53	GPT-4.1 nano OpenAI	0.29
54	GPT-4o OpenAI	0.13